Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3291 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.7742. Min Act: -0.1700
Data Index: 5719410 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.7429. Min Act: -0.1700
Data Index: 2421017 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.7117. Min Act: -0.1700
Data Index: 5200585 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.7117. Min Act: -0.1700
Data Index: 2300710 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.6804. Min Act: -0.1700
Data Index: 355500 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.6804. Min Act: -0.1700
Data Index: 5865813 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.6804. Min Act: -0.1700
Data Index: 5198434 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.5867. Min Act: -0.1700
Data Index: 5024264 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.6179. Min Act: -0.1700
Data Index: 8154475 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.5554. Min Act: -0.1700
Data Index: 2874199 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.5554. Min Act: -0.1700
Data Index: 354825 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.5554. Min Act: -0.1700
Data Index: 4965447 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4929. Min Act: -0.1700
Data Index: 5501010 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4929. Min Act: -0.1700
Data Index: 3122423 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4617. Min Act: -0.1700
Data Index: 7214241 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4617. Min Act: -0.1700
Data Index: 8734516 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4304. Min Act: -0.1700
Data Index: 3614382 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4304. Min Act: -0.1700
Data Index: 7381458 (Open Web Text)
Max Activating Token Index: 124
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4617. Min Act: -0.1700
Data Index: 6136305 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7742. Min Range: -5.7742
Max Act: 5.4617. Min Act: -0.1700
Data Index: 5200589 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #19